INDEX
Explanations
phrases related to government officials and military topics
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1108
+0.12
0.3%
1415
+0.09
0.3%
2016
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1415
+0.12
0.02
2016
+0.09
0.05
441
+0.09
0.04
Negative Logits
<bos>
-0.64
prêtres
-0.63
kinci
-0.57
skimage
-0.56
riguard
-0.56
tolu
-0.55
provinciale
-0.55
pymysql
-0.54
gabri
-0.54
créées
-0.54
POSITIVE LOGITS
respectively
0.83
collectively
0.75
all
0.73
allemaal
0.72
respectively
0.70
모두
0.63
respectivamente
0.62
それぞれ
0.60
all
0.59
each
0.56
Activations Density 0.553%